← Search

Giri Narasimhan

3 accepted papers

2026

Deep Learning and Foundation Models for Weather Prediction: A Survey

IJCAI 2026

Numerical weather prediction (NWP) models remain the cornerstone of atmospheric sciences. Yet, deep learning (DL) is challenging this paradigm by its ability to capture intricate spatio-temporal patterns and deliver ultra-fast predictions. Analogous to the foundation models (e.g., ChatGPT) in natura

Cited by 0Scholar
2025

CoDiCast: Conditional Diffusion Model for Global Weather Forecasting with Uncertainty Quantification

IJCAI 2025

Accurate weather forecasting is critical for science and society. However, existing methods have not achieved the combination of high accuracy, low uncertainty, and high computational efficiency simultaneously. On one hand, traditional numerical weather prediction (NWP) models are computationally in

2025

FIDLAR: Forecast-Informed Deep Learning Architecture for Flood Mitigation

AAAI 2025technical

In coastal river systems, floods, often during major storms or king tides, severely threaten lives and property. However, hydraulic structures such as dams, gates, pumps, and reservoirs exist in these river systems, and these floods can be mitigated or even prevented by strategically releasing water…